{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OGJE2EYOZMEF3VQYSIVRQTVH6M","short_pith_number":"pith:OGJE2EYO","schema_version":"1.0","canonical_sha256":"71924d130ecb085dd618922b184ea7f32c8279f2e746b6e2109f39de95d27be9","source":{"kind":"arxiv","id":"2402.03126","version":3},"attestation_state":"computed","paper":{"title":"How Free is Parameter-Free Stochastic Optimization?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Attia, Tomer Koren","submitted_at":"2024-02-05T15:51:49Z","abstract_excerpt":"We study the problem of parameter-free stochastic optimization, inquiring whether, and under what conditions, do fully parameter-free methods exist: these are methods that achieve convergence rates competitive with optimally tuned methods, without requiring significant knowledge of the true problem parameters. Existing parameter-free methods can only be considered ``partially'' parameter-free, as they require some non-trivial knowledge of the true problem parameters, such as a bound on the stochastic gradient norms, a bound on the distance to a minimizer, etc. In the non-convex setting, we dem"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.03126","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T15:51:49Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5ed740b23fa795e96e0d518aab67d77fd9441f0dc0e4c440acac83a60b9b6c44","abstract_canon_sha256":"93dc06bcdbeb4884fe82d5dd4ac32a7b6b85973d57e696dc4044521a0c26e900"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:02.724054Z","signature_b64":"1c9QgiGyVz9cWm2EqOmaZwEzJq/aLNx6kKkRf8l6jdKle1mZqqbm+sY3tCCOy7WxwdDZO7s4AzHLQyLPhE5DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71924d130ecb085dd618922b184ea7f32c8279f2e746b6e2109f39de95d27be9","last_reissued_at":"2026-07-05T09:23:02.723608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:02.723608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Free is Parameter-Free Stochastic Optimization?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Attia, Tomer Koren","submitted_at":"2024-02-05T15:51:49Z","abstract_excerpt":"We study the problem of parameter-free stochastic optimization, inquiring whether, and under what conditions, do fully parameter-free methods exist: these are methods that achieve convergence rates competitive with optimally tuned methods, without requiring significant knowledge of the true problem parameters. Existing parameter-free methods can only be considered ``partially'' parameter-free, as they require some non-trivial knowledge of the true problem parameters, such as a bound on the stochastic gradient norms, a bound on the distance to a minimizer, etc. In the non-convex setting, we dem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03126","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.03126/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.03126","created_at":"2026-07-05T09:23:02.723664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03126v3","created_at":"2026-07-05T09:23:02.723664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03126","created_at":"2026-07-05T09:23:02.723664+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGJE2EYOZMEF","created_at":"2026-07-05T09:23:02.723664+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGJE2EYOZMEF3VQY","created_at":"2026-07-05T09:23:02.723664+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGJE2EYO","created_at":"2026-07-05T09:23:02.723664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14970","citing_title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M","json":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M.json","graph_json":"https://pith.science/api/pith-number/OGJE2EYOZMEF3VQYSIVRQTVH6M/graph.json","events_json":"https://pith.science/api/pith-number/OGJE2EYOZMEF3VQYSIVRQTVH6M/events.json","paper":"https://pith.science/paper/OGJE2EYO"},"agent_actions":{"view_html":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M","download_json":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M.json","view_paper":"https://pith.science/paper/OGJE2EYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03126&json=true","fetch_graph":"https://pith.science/api/pith-number/OGJE2EYOZMEF3VQYSIVRQTVH6M/graph.json","fetch_events":"https://pith.science/api/pith-number/OGJE2EYOZMEF3VQYSIVRQTVH6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M/action/storage_attestation","attest_author":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M/action/author_attestation","sign_citation":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M/action/citation_signature","submit_replication":"https://pith.science/pith/OGJE2EYOZMEF3VQYSIVRQTVH6M/action/replication_record"}},"created_at":"2026-07-05T09:23:02.723664+00:00","updated_at":"2026-07-05T09:23:02.723664+00:00"}